---
title: Qwen2.5-VL-7B-Instruct | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct
description: Instruction-tuned multimodal vision-language model
---
# Qwen2.5-VL-7B-Instruct

![Qwen2.5-VL-7B-Instruct](https://assets.runware.ai/covers/alibaba-qwen2-5-vl-7b-instruct.jpg)

Qwen2.5-VL-7B-Instruct is a multimodal model that processes images and text together to perform visual reasoning, captioning, question answering, and structured output generation. It integrates a vision encoder with a 7B instruction-tuned language backbone to support rich interactive multimodal understanding.

- **Status**: live
- **ID**: `alibaba-qwen2-5-vl-7b-instruct`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: August 24, 2023
- **Zero Data Retention**: Yes
- **Capabilities**: Image to Text, Caption, Checkpoint

## Pricing

$0.003 from, per run · ~6s per request

**Measured runs**

- 1024×1024 input: `$0.003` (~5s)

**4 example generations**

- [caption](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct/examples#example-auction-furniture-lot-caption): `$0.0013` (~6s)
- [caption](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct/examples#example-culinary-magazine-photo-caption): `$0.0013` (~6s)
- [caption](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct/examples#example-vehicle-damage-intake-caption): `$0.0019` (~7s)
- [caption](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct/examples#example-wildfire-response-editorial-photo-caption): `$0.0032` (~9s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `caption`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [webhookURL](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [includeCost](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [image](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-inputs-image)

- **Path**: `inputs.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba-qwen2-5-vl-7b-instruct`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [prompt](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#request-prompt)

- **Type**: `string`

Instructions or questions to guide the image analysis.

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `caption`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [text](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#response-text)

- **Type**: `string`
- **Required**: true

Generated caption text describing the input.

### [cost](https://runware.ai/docs/models/alibaba-qwen2-5-vl-7b-instruct#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### caption (caption)

```
The photograph showcases a vintage-style armchair positioned centrally within a softly-lit, minimalist room. The chair boasts a rich, dark wood frame exhibiting subtle distresss and a glossy, polished-like sheen indicative of polished or lacquered craftsmanship. Its curved-back and rounded-shaped legs contribute to a classic, slightly-form, while the woven-patterned cane detailing along the sides adds a touch of artisanal sophistication.
```

```json
{
  "taskType": "caption",
  "taskUUID": "3f81f9fe-4859-474b-856b-34f5e275adf5",
  "model": "runware:152@2",
  "prompt": "Write one accurate, detailed auction-catalog caption describing only what is visibly present in this photograph. Identify the primary furniture item, then describe its apparent form, colors, surface qualities, construction details, upholstery, viewpoint, visible wear or condition, placement, surrounding objects, lighting, and composition. Do not infer a designer, maker, date, provenance, authenticity, exact materials, dimensions, or historical style unless directly visible. Use precise, neutral language in a single paragraph of 90–130 words.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/0c273ba3-e0e3-439a-be77-1e6eb6586fcd.jpg"
  }
}
```

---

### caption (caption)

```
The image shows a white van parked on a wet asphalt surface near a sidewalk. The vehicle's front left side is significantly damaged, with noticeable dents and scratches on the fender and door. The headlight on the same side is intact but appears slightly misaligned. Debris, including small fragments of metal and plastic, is scattered on the ground around the van, suggesting recent impact. The windshield has a visible crack running across it.
```

```json
{
  "taskType": "caption",
  "taskUUID": "49df496f-52be-4470-a0a1-f5970bce80dd",
  "model": "runware:152@2",
  "prompt": "Write an accurate, detailed insurance intake caption for this image. Identify the primary vehicle, camera viewpoint, visible damage, affected exterior components, debris, road and weather conditions, and relevant surroundings. Distinguish clearly between what is visibly damaged and what merely appears intact. Ground every statement only in observable image content; do not infer the cause of damage, mechanical condition, ownership, injuries, fault, location, or repair cost. Use one concise paragraph.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/3bd27eff-b313-4093-a524-39cc5eafab0b.jpg"
  }
}
```

---

### caption (caption)

```
A firefighter in a yellow protective suit and red helmet stands amidst an orange grove, actively using a hose to combat a small but intense fire. The ground around the firefighter is scorched black, with visible embers and flames still burning. In the background, a fire truck with its lights on is parked, suggesting ongoing firefighting efforts. The setting appears to be a rural area with multiple orange trees, some of which have ripe fruit still hanging.
```

```json
{
  "taskType": "caption",
  "taskUUID": "0b76ae3b-de81-4872-a888-b9003807d77c",
  "model": "runware:152@2",
  "prompt": "Write one accurate, detailed editorial caption describing only what is visibly present in this photograph. Identify the primary subject, clothing and equipment, observable action, setting, background activity, lighting, and signs of fire damage. Use clear newsroom prose and present tense. Do not guess the person's identity, exact location, date, agency, cause of the fire, or any facts that cannot be verified from the image.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/3d686d76-b572-4054-9b36-bfe91477888e.jpg"
  }
}
```

---

### caption (caption)

```
In a professional kitchen bathed in softlight, a chef meticulously craftsurs a lemon meringue tart atop a pristine white plate. With practiced hand, he wields a culinary torch, its blue flame dancinging gently across the toasted's crisp, craftinging a caramelized allure atop the creamy custard. The pastry, crowned with a plush, puffy cloud of toasted, restsands proudlyly amidst brass of gleaming copper potsers and a bowl of vibrant, sliced lemon.
```

```json
{
  "taskType": "caption",
  "taskUUID": "85420125-6c48-4dd6-9f66-2fb7fefbc5b1",
  "model": "runware:152@2",
  "prompt": "Write an accurate, detailed editorial photo caption of 70–100 words. Describe the primary subject, the visible action, the dessert, relevant kitchen tools, surrounding activity, lighting, and composition. Ground every statement only in what can be directly observed in the image. Do not invent the chef's name, restaurant, location, recipe, occasion, emotions, or culinary technique beyond what is visibly evident. Use polished present-tense language suitable for a culinary magazine photo desk.",
  "inputs": {
    "image": "https://assets.runware.ai/assets/inputs/b6720366-67fd-4ddf-9605-55b7c299bf7d.jpg"
  }
}
```